lyt-image-to-prompt
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and configuration files contain no signs of malicious intent, prompt injection, or obfuscation.
- [DATA_EXPOSURE]: Analysis confirms the skill does not attempt to access sensitive local files or hardcoded credentials. It operates strictly on user-provided image and text data for commercial visual tasks.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external network operations or download untrusted code. It references a local common-rules file (
../lyt/references/common-rules.md) which is standard for modular skill development. - [COMMAND_EXECUTION]: There are no patterns of subprocess spawning, shell command execution, or dynamic code execution (eval/exec) within the provided files.
- [PROMPT_INJECTION]: The instructions maintain clear task boundaries for processing ecommerce visuals and explicitly prohibit the agent from guessing information not visible in the images or performing unrelated tasks like business diagnosis.
Audit Metadata